The study in this abstract aimed to use a CT-based radiomics model to predict the histopathological subtype of non-small cell lung cancer (NSCLC) patients. The study included 678 patients, with 531 used for training and 147 for testing. The robust radiomics features extracted from the CT scans were used to train a support vector machine (SVM) classifier, which achieved an accuracy of 0.80 on the training set and 0.77 on the test set. The study showed that CT-based radiomics can accurately predict the histopathology subtype of NSCLC patients, offering a less invasive and more cost-effective alternative to traditional tissue analysis methods.